Write the spec. Let the agents build. Ship with confidence. Agent-powered development changes how we build—but clarity still starts with humans. In this upcoming New Breakpoint, Arnaud Lheureux and Michelle Sandford share a practical playbook for treating the spec as the product, and using agents to do the heavy lifting. 🔍 You’ll learn: • What makes a spec implementable (outcomes, non-goals, edge cases & acceptance criteria) • How to translate specs into high-quality agent tasks • Prompting patterns and review checkpoints that actually work • How to avoid scope creep and “plausible but wrong” code • How teams operationalize this approach with GitHub Enterprise 📅 12 March 2026 ⏰ 12:30–1:30 PM (UTC+11) If you want a repeatable way to go from spec → merged PR with less toil and fewer surprises, this session is for you. 👉 Secure your spot now! https://msft.it/6044QZHQe #NewBreakpoint #DeveloperProductivity #AgentPoweredDevelopment #GitHubEnterprise #SoftwareEngineering #DevTools #MicrosoftDevelopers
Microsoft Reactor
Technology, Information and Internet
Redmond, Washington 47,921 followers
Learn. Connect. Build.
About us
Ready to get started with AI and the latest technologies? Microsoft Reactor provides events, training, and community resources to help developers, entrepreneurs and startups build on AI technology and more. Join us!
- Website
-
https://developer.microsoft.com/reactor
External link for Microsoft Reactor
- Industry
- Technology, Information and Internet
- Company size
- 10,001+ employees
- Headquarters
- Redmond, Washington
- Specialties
- technology, AI, students, cloud computing, Microsoft, and Azure
Updates
-
🚀 Write the Spec, Let the Agents Build: A Practical Playbook Agent-powered dev can speed things up—but only if the spec is clear and constrained. In this episode of New Breakpoint, Arnaud Lheureux joins Michelle Sandford for a hands-on guide to shipping with confidence in an agent-powered world. ✅ What we’ll cover: • How to write implementable specs: clear outcomes, non-goals, edge cases, acceptance criteria • Defining the smallest testable slice • Turning specs into high-quality agent tasks for implementation, tests, refactors, and docs • Prompting patterns + review checkpoints to keep humans in control • Avoiding common failures: scope creep, plausible-but-wrong code, inconsistent environments • Enterprise lens: operationalizing with GitHub Enterprise, governance + security boundaries 📅 12 March 2026 ⏰ 12:30 PM – 1:30 PM (UTC+11) 🔗 Secure your spot! https://msft.it/6048QZH42 If you want a repeatable workflow from spec → merged pull request with less toil and fewer surprises, this is for you. #NewBreakpoint #DeveloperProductivity #SoftwareEngineering #GitHubEnterprise #DevTools
-
-
Get a practical introduction to building AI agents using the AI Toolkit Extension for VS Code. We’ll walk through agent design (core architecture), prompt engineering, function calling and MCP-powered tool use, tracing and evaluation using the extension. Expect a focused, actionable session that shows how to build agents that are reliable, observable, and ready for real-world scenarios. 🔗 The Java Script AI Build-a-thon: https://lnkd.in/gJX4B3Qa 📌 This session is a part of a series, learn more here: https://lnkd.in/gFP9yTY8 #MicrosoftReactor #learnconnectbuild
Design & Build an Agent E2E with Agent Builder (AITK)
www.linkedin.com
-
Want to plan, build, evaluate, customize, and deploy your agentic AI solutions right from your IDE? The AI Toolkit accelerates end-to-end developer experiences with Microsoft Foundry directly in Visual Studio Code. Join Leo Yao as he showcases the AI Toolkit and demonstrates how it accelerates your development workflow. Learn how to plan, build, evaluate, customize, and deploy agentic AI solutions directly from Visual Studio Code with seamless Microsoft Foundry integration. Customer Spotlight - Arize AI 🔎 Explore the repo: https://lnkd.in/eugEFQCA 📢 Continue the conversation on the Discord: https://lnkd.in/gWjs8Bw6 📌 This session is a part of a series! Learn more here: https://lnkd.in/gYVJa8Ee #MicrosoftReactor #learnconnectbuild [eventID:26828]
Model Mondays - AI Developer Experiences
www.linkedin.com
-
One agent is powerful. Multiple agents working together? That's transformational. In this session, we explore multi-agent orchestration patterns: how to design agent teams, delegate tasks, and coordinate complex workflows. Using Microsoft Agent Framework and Microsoft Foundry, you'll see how to build agent systems that divide and conquer problems too complex for a single agent. What you'll learn: • When single agents aren't enough (and when they are) • Multi-agent architecture patterns: delegation, collaboration, debate • Building agent teams with Microsoft Agent Framework • Coordinating complex workflows across agents • Real-world use cases: research assistants, code review teams, customer service escalation Who should attend: Developers who've built their first agent and want to scale up to multi-agent solutions. 🔎 https://lnkd.in/gh_p8z4d 🔎 https://lnkd.in/gckQSa39 📌 This session is a part of a series - learn more here: https://lnkd.in/g6JQY6NN #MicrosoftReactor #learnconnectbuild
When Agents Work Together: Multi-Agent Orchestration on Azure
www.linkedin.com
-
🚀 GitHub Copilot Dev Days are coming March 15–April 30! Attend an event near you! Have a user group? Host a meetup in your city and help developers explore the power of GitHub Copilot with free, high-quality training materials. Find an event or sign up to host: https://msft.it/6040QjKbj
-
🔍 Decode what’s next on Azure—this March at Microsoft Reactor Azure Decoded is back with four live, hands‑on sessions designed to help developers make sense of modern Azure scenarios—from AI agents and cloud security to migration, governance, and modernization. Join Microsoft experts each week for live demos, practical walkthroughs, and interactive Q&A you can apply immediately. 🗓 All sessions stream live at 12 PM PT March lineup: • March 4 – When Agents Work Together: Multi‑Agent Orchestration on Azure • March 11 – Getting Ready for the Migrate & Modernize Summit • March 18 – Kickstart AI Security with Defender for Cloud • March 25 – Governance in a Modern Lakehouse with Azure Databricks and OneLake ✅ Free to attend ✅ Weekly, hands‑on learning ✅ Built for real‑world Azure scenarios 👉 Register once to access the full series: https://msft.it/6047QZSfl #MicrosoftReactor #AzureDecoded #MicrosoftAzure #CloudComputing #AI #CloudSecurity #AzureDatabricks #Developers #TechEvents
-
-
In this session, we explore the end-to-end journey of designing and developing AI solutions with Microsoft Foundry models. The session is structured around four key phases of the model development journey. We begin with Model Understanding, where you discover the Foundry model catalog and build intuition around core model capabilities. Next is Model Selection, focusing on how to choose the right model for a given use case using benchmarks, evaluations, and leaderboards. We then move into Model Customization, covering how models can be adapted through techniques such as context engineering, fine‑tuning, and compression to better meet application needs. Finally, we close with Model Observability, highlighting how evaluations, tracing, and monitoring help ensure models behave safely, reliably, and effectively at scale. 🔗 The Java Script AI Build-a-thon: https://lnkd.in/gJX4B3Qa 📌 This session is a part of a series, learn more here: https://lnkd.in/gFP9yTY8 #MicrosoftReactor #learnconnectbuild [eventID:26773]
End-to-End Model Development on Microsoft Foundry
www.linkedin.com
-
Tomorrow! 🚀 Maximize the Cost Efficiency of AI Agents on Azure March 5, 2026 ⏰ Time: 8:00 AM PT / 6:00 PM IDT / 3:00 PM GMT Whether you’re building, scaling, or optimizing AI agents, this session will help you: Think strategically about cost vs. value Make informed decisions that protect your budget Ensure your AI agent projects deliver maximum impact over time 🔗 Save your spot: https://msft.it/6042QzZKI #Azure #AI #AIAgents #CostEfficiency #ROI #Cloud #Reactor #Developers
-
-
This session breaks down advanced RAG patterns, from chunking and embeddings to similarity metrics, vector storage, retrieval strategies, and LLM chain responses. We’ll also explore streaming, chat history, and where GraphRAG fits in. You’ll leave with a clear blueprint for building accurate, optimized RAG pipelines for personal or enterprise-scale scenarios. Guided project: You’ll build a local serverless RAG chat app using CodeTours covering architecture, ingestion, Cosmos DB/FAISS storage, retrieval, and response generation. By the end, you’ll have a working repo plus practical intuition for tuning chunking, similarity, and evaluation. 🔗 The Java Script AI Build-a-thon: https://lnkd.in/gJX4B3Qa 📌 This session is a part of a series, learn more here: https://lnkd.in/gFP9yTY8 #MicrosoftReactor #learnconnectbuild
Advanced Retrieval Augmented Generation (RAG) Deep Dive
www.linkedin.com